osobh and Claude Opus 4.7
6d59251c51
rtx-nn / rtx-multimodal: cargo fmt reformatting
...
Pure formatting changes across rtx-nn (conv_transpose1d, conv/mod, rnn/lstm)
and rtx-multimodal (audio/generation, audio/source_separation): multi-line
braces, trailing commas, import ordering. No logic changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]
2026-04-27 18:37:07 -07:00
osobh and Claude Opus 4.6
85b77d49f2
Add audio neural layers and model architectures for ClawSample integration
...
New nn layers:
- ConvTranspose1d with stride, padding, output_padding (9 tests)
- LSTM/BiLSTM with multi-layer support and hidden state (10 tests)
Audio source separation:
- Demucs ONNX inference with segmented overlap-add processing
- Native HtDemucs architecture (encoder/decoder with BiLSTM bottleneck)
- StemType enum: vocals, drums, bass, other, piano, guitar
Audio generation:
- Stable Audio Open ONNX inference scaffold
- GenerationParams (prompt, duration, steps, cfg_scale, seed)
ONNX export scripts:
- export_demucs_onnx.py — Demucs v4 to ONNX with segment chunking
- export_stable_audio_onnx.py — Stable Audio Open components
- export_mert_onnx.py — MERT music understanding transformer
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]
2026-04-17 12:27:12 -07:00
